dflow MCP server
✓ OfficialAccess Kalshi prediction market data including events, markets, trades, and real-time forecast analytics.
Also known as openSVM/dflow-mcp
- Stars
- 7
- Tools
- 23
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Dec 2, 2025
- License
- Unlicense
What is dflow MCP?
dflow accesses Kalshi prediction market data including events, markets, trades, and real-time forecast analytics. It exposes 23 tools, such as get_event, get_events, get_market.
Summary generated from the project's README
About dflow MCP server
Analyzing Kalshi prediction market trends and real-time forecast analytics from within an AI client is what this tool enables. Developers can interact with the first CFTC-regulated exchange for real-world event trading by using 23 specialized tools. These tools provide access to event metadata, market details, trade histories, and candlestick data for both events and markets.
Users can set up the system locally using Smithery for automatic configuration with Claude Desktop or through a manual installation using Bun or Node.js. It operates via stdio transport and is compatible with various clients like Cursor and Continue. Users can perform complex queries such as retrieving forecast percentile history, searching for specific events by title, and fetching live milestone data.
What you can do with it
- 1Finding specific prediction eventsYou can ask the AI to search for upcoming elections or other events using keywords.
- 2Tracking forecast percentile changesAn AI client can retrieve historical forecast data to see how market sentiment has shifted over time.
- 3Reviewing recent trade activityUsers can pull trade histories for specific markets to understand recent transaction volume.
Written from the project's README. Every use case is checked against a quote from it.
dflow MCP tools 23
Detected from the READMEget_eventget_eventsget_marketget_market_by_mintget_marketsget_markets_batchget_tradesget_trades_by_mintget_forecast_percentile_historyget_forecast_percentile_history_by_mintget_event_candlesticksget_market_candlesticks
| get_event | — | |
| get_events | — | |
| get_market | — | |
| get_market_by_mint | — | |
| get_markets | — | |
| get_markets_batch | — | |
| get_trades | — | |
| get_trades_by_mint | — | |
| get_forecast_percentile_history | — | |
| get_forecast_percentile_history_by_mint | — | |
| get_event_candlesticks | — | |
| get_market_candlesticks | — |
Show all 23 toolsShow fewer tools
get_market_candlesticks_by_mintget_live_dataget_live_data_by_eventget_live_data_by_mintget_seriesget_series_by_tickerget_outcome_mintsfilter_outcome_mintsget_tags_by_categoriesget_filters_by_sportssearch_events
| get_market_candlesticks_by_mint | — | |
| get_live_data | — | |
| get_live_data_by_event | — | |
| get_live_data_by_mint | — | |
| get_series | — | |
| get_series_by_ticker | — | |
| get_outcome_mints | — | |
| filter_outcome_mints | — | |
| get_tags_by_categories | — | |
| get_filters_by_sports | — | |
| search_events | — |
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableopensvm/dflow-mcp is public and reachablegithub.com/opensvm/dflow-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Unlicensespdx.org/licenses/Unlicense.html ↗Pass
- Commit or release in the last yearLast commit or release 2025-12-02github.com/opensvm/dflow-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model23 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubDFlow MCP Server
Access Kalshi prediction market data - the first CFTC-regulated exchange for trading on real-world events. Built by OpenSVM. 23 tools for events, markets, trades, forecasts, candlesticks and live data.
Demo: https://dflow.opensvm.com
Features
This MCP server provides access to the complete Prediction Market Metadata API including:
- Event Management: Get events, search events, retrieve event metadata
- Market Data: Market information, batch queries, market lookups by mint
- Trading Data: Trade history, trades by market, pagination support
- Forecast Analytics: Forecast percentile history, time series data
- Candlestick Data: OHLC data for events and markets
- Live Data: Real-time data feeds, milestone information
- Series Information: Series templates, categories, and metadata
- Utility Functions: Outcome mint queries, filtering, and search capability
Installation
Method 1: Install via Smithery (Recommended)
The easiest way to install this MCP server is through Smithery:
npx @smithery/cli install dflow-mcp-server --client claude
This will automatically configure the server for use with Claude Desktop.
Method 2: Manual Installation
Prerequisites
- Bun (recommended) or Node.js 18+
Install Dependencies
bun install
Usage
Starting the Server
# Development mode (with hot reload)
bun run dev
# Production mode
bun start
# Or directly with Bun
bun run src/index.ts
The server uses stdio transport for MCP communication, which is the standard for MCP clients.
Integration with MCP Clients
Claude Desktop
If you installed via Smithery, the configuration is automatic. For manual setup, add this to your Claude Desktop config:
{
"mcpServers": {
"dflow-mcp": {
"command": "bun",
"args": ["run", "/path/to/dflow-mcp/src/index.ts"]
}
}
}
Other MCP Clients
This server is compatible with any MCP client (Cursor, Continue, etc.). Use the same configuration format as above.
Available Tools
Event Tools
get_event- Get a single event by tickerget_events- Get paginated list of all events
Market Tools
get_market- Get market details by tickerget_market_by_mint- Get market by mint addressget_markets- Get paginated list of marketsget_markets_batch- Get multiple markets (up to 100)
Trade Tools
get_trades- Get trades across marketsget_trades_by_mint- Get trades for specific market
Analytics Tools
get_forecast_percentile_history- Get forecast historyget_forecast_percentile_history_by_mint- Forecast history by mintget_event_candlesticks- Event candlestick dataget_market_candlesticks- Market candlestick dataget_market_candlesticks_by_mint- Candlesticks by mint
Live Data Tools
get_live_data- Get live data for milestonesget_live_data_by_event- Live data for eventget_live_data_by_mint- Live data by mint
Series Tools
get_series- Get all series templatesget_series_by_ticker- Get specific series
Utility Tools
get_outcome_mints- Get outcome mint addressesfilter_outcome_mints- Filter addresses to outcome mintsget_tags_by_categories- Get category-tag mappingget_filters_by_sports- Get sports filtering optionssearch_events- Search events by title/ticker
Example Tool Calls
Get a specific event
{
"tool": "get_event",
"arguments": {
"event_id": "US-PRESIDENT-2024",
"withNestedMarkets": true
}
}
Get market by mint address
{
"tool": "get_market_by_mint",
"arguments": {
"mint_address": "9WzDXwBbmkg8ZTbNMqUxvQRAyrZzDsGYdLVL9zYtAWWM"
}
}
Get forecast history
{
"tool": "get_forecast_percentile_history",
"arguments": {
"series_ticker": "US-PRESIDENT",
"event_id": "US-PRESIDENT-2024",
"percentiles": "25,50,75",
"startTs": 1704067200,
"endTs": 1706745600,
"periodInterval": 3600
}
}
Search events
{
"tool": "search_events",
"arguments": {
"q": "election",
"limit": 10,
"sort": "volume",
"order": "desc"
}
}
Development
Project Structure
dflow-mcp/
├── src/
│ └── index.ts # Main server implementation
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── llms_dflow.json # API specification
└── README.md # This file
Building
bun run build
Testing
bun run test
API Details
The server implements the complete REST API defined in llms_dflow.json with the following base URL:
https://prediction-markets-api.dflow.net
All tools include comprehensive parameter validation and type definitions. Error handling returns informative messages for debugging.
Publishing to Smithery
This server is configured for publication on Smithery, the MCP server registry.
Configuration Files
smithery.yaml- Defines the runtime (TypeScript) and target (local)package.json- Includes module entry point and Smithery CLI scripts
To Publish
- Ensure your code is pushed to a public GitHub repository
- Visit smithery.ai/new
- Connect your GitHub repository
- Smithery will automatically detect the
smithery.yamlconfiguration
Once published, users can install your server with:
npx @smithery/cli install dflow-mcp-server --client claude
License
MIT License - See LICENSE file for details.
OpenSVM × Kalshi × DFlow
dflow MCP questions
What tools does dflow MCP provide?
It exposes 23 tools, including get_event, get_events, get_market, get_market_by_mint, get_markets.
What kind of data can I access with this server?
You can access event management tools, market information, trade history, forecast analytics, candlestick data, and real-time live data feeds.
Is this server compatible with Cursor or Continue?
Yes, the server is compatible with any MCP client including Cursor and Continue.